Chat · Text · Chinese Leaderboard

Ranking for Text / Chinese, based on public preference data.

Selection guide

Chinese model ranking guide

Ranking for Text / Chinese, based on public preference data.

gpt-5.5claude-opus-4-6-thinkingclaude-opus-4-6qwen3.5-max-previewgpt-5.5-high
Current DirectoryChat · Text · Chinese
Models330
Published2026/05/27
Arena public preference evaluationOriginal leaderboard: Text / ChinesePublished: 2026/05/27Leaderboard dataset: LMArena latest parquetOpen Arena sourceOpen leaderboard dataset
1
gpt-5.5
Openai
100.0
808
1.05M
¥36 / ¥216Input/Output
2
claude-opus-4-6-thinking
Anthropic
99.7
1.8K
1M
¥36 / ¥180Input/Output
3
claude-opus-4-6
Anthropic
99.4
1.9K
1M
¥36 / ¥180Input/Output
4
qwen3.5-max-preview
Alibaba
99.1
1.2K
-
-
5
gpt-5.5-high
Openai
98.8
812
1.05M
¥36 / ¥216Input/Output
6
claude-opus-4-7-thinking
Anthropic
98.5
1.1K
1M
¥36 / ¥180Input/Output
7
gemini-3.1-pro-preview
Google
98.2
2.3K
1.05M
¥14.4 / ¥86.4Input/Output
8
claude-opus-4-7
Anthropic
97.9
1K
1M
¥36 / ¥180Input/Output
9
qwen3.7-max-preview
Alibaba
97.6
268
1M
¥18 / ¥54Input/Output
10
kimi-k2.6
Moonshot
97.3
808
262K
¥6.84 / ¥28.8Input/Output
11
gemini-3-pro
Google
97.0
2.1K
1.05M
¥14.4 / ¥86.4Input/Output
12
gemini-3.5-flash
Google
96.7
492
1.05M
¥10.8 / ¥64.8Input/Output
13
gpt-5.4
Openai
96.4
1.7K
1.05M
¥18 / ¥108Input/Output
14
gpt-5.4-high
Openai
96.0
1.5K
1.05M
¥18 / ¥108Input/Output
15
glm-5
Zai
95.7
1.1K
205K
¥7.2 / ¥23Input/Output
16
glm-5.1
Zai
95.4
843
200K
¥0 / ¥0Input/Output
17
gemini-3-flash
Google
95.1
1.5K
1.05M
¥3.6 / ¥21.6Input/Output
18
ernie-5.1
Baidu
94.8
692
119K
¥5.4 / ¥21.6Input/Output
19
muse-spark
Meta
94.5
723
-
-
20
dola-seed-2.0-pro
Bytedance
94.2
2K
-
-
21
gemini-2.5-pro
Google
93.9
6.3K
1.05M
¥9 / ¥72Input/Output
22
kimi-k2.5-thinking
Moonshot
93.6
1.7K
262K
¥4.32 / ¥21.6Input/Output
23
qwen3.5-397b-a17b
Alibaba
93.3
1.6K
262K
¥3.1 / ¥18.6Input/Output
24
ernie-5.0-preview-1022
Baidu
93.0
280
128K
¥7.92 / ¥14.4Input/Output
25
deepseek-v4-pro
Deepseek
92.7
936
1M
¥3.13 / ¥6.26Input/Output
26
ernie-5.0-0110
Baidu
92.4
1.6K
128K
¥7.92 / ¥14.4Input/Output
27
glm-4.6
Zai
92.1
1.6K
205K
¥4.32 / ¥15.8Input/Output
28
mimo-v2.5-pro
Xiaomi
91.8
849
1.05M
¥7.2 / ¥21.6Input/Output
29
deepseek-v4-pro-thinking
Deepseek
91.5
842
1M
¥3.13 / ¥6.26Input/Output
30
gpt-5.1-high
Openai
91.2
2K
400K
¥9 / ¥72Input/Output
31
qwen3-max-preview
Alibaba
90.9
1.5K
262K
¥6.2 / ¥24.8Input/Output
32
grok-4.20-beta-0309-reasoning
Xai
90.6
1.5K
2M
¥14.4 / ¥43.2Input/Output
33
glm-4.7
Zai
90.3
688
205K
¥0 / ¥0Input/Output
34
qwen3.6-max-preview
Alibaba
90.0
283
246K
¥9.5 / ¥56.9Input/Output
35
claude-sonnet-4-6
Anthropic
89.7
1.3K
1M
¥21.6 / ¥108Input/Output
36
grok-4.20-multi-agent-beta-0309
Xai
89.4
1.5K
2M
¥14.4 / ¥43.2Input/Output
37
ernie-5.0-preview-1203
Baidu
89.1
534
128K
¥7.92 / ¥14.4Input/Output
38
gemini-3-flash (thinking-minimal)
Google
88.8
2.6K
1.05M
¥3.6 / ¥21.6Input/Output
39
grok-4.20-beta1
Xai
88.4
1.2K
2M
¥14.4 / ¥43.2Input/Output
40
gemma-4-26b-a4b
Google
88.1
383
262K
¥0.94 / ¥2.88Input/Output
41
qwen3.6-plus
Alibaba
87.8
902
1M
¥3.6 / ¥21.6Input/Output
42
gpt-5.1
Openai
87.5
2K
400K
¥9 / ¥72Input/Output
43
grok-4-fast-chat
Xai
87.2
358
2M
¥1.44 / ¥3.6Input/Output
44
mimo-v2.5
Xiaomi
86.9
766
1.05M
¥2.88 / ¥14.4Input/Output
45
claude-opus-4-5-20251101
Anthropic
86.6
3.3K
200K
¥36 / ¥180Input/Output
46
qwen3.5-27b
Alibaba
86.3
1.4K
262K
¥2.16 / ¥17.3Input/Output
47
deepseek-v4-flash-thinking
Deepseek
86.0
883
1M
¥1.01 / ¥2.02Input/Output
48
gemma-4-31b
Google
85.7
364
262K
¥3.24 / ¥7.2Input/Output
49
grok-4.1
Xai
85.4
3.5K
200K
¥14.4 / ¥72Input/Output
50
qwen3-next-80b-a3b-instruct
Alibaba
85.1
1.2K
131K
¥1.04 / ¥4.13Input/Output
51
qwen3-235b-a22b-thinking-2507
Alibaba
84.8
413
131K
¥2.07 / ¥8.26Input/Output
52
deepseek-v3.1-thinking
Deepseek
84.5
874
128K
¥1.44 / ¥5.04Input/Output
53
glm-4.5
Zai
84.2
1.3K
131K
¥4.32 / ¥15.8Input/Output
54
deepseek-v4-flash
Deepseek
83.9
848
1M
¥1.01 / ¥2.02Input/Output
55
qwen3.5-35b-a3b
Alibaba
83.6
1.5K
262K
¥1.8 / ¥14.4Input/Output
56
gpt-5.2-chat-latest-20260210
Openai
83.3
1.6K
400K
¥12.6 / ¥101Input/Output
57
amazon-nova-experimental-chat-11-10
Amazon
83.0
1.2K
-
-
58
qwen3.5-122b-a10b
Alibaba
82.7
1.5K
262K
¥2.88 / ¥23Input/Output
59
qwen3-235b-a22b-instruct-2507
Alibaba
82.4
4.8K
128K
¥2.09 / ¥8.23Input/Output
60
qwen3.5-flash
Alibaba
82.1
1.5K
1M
¥1.24 / ¥12.4Input/Output
61
longcat-flash-chat-2602-exp
Meituan
81.8
1.3K
128K
¥1.08 / ¥10.8Input/Output
62
deepseek-v3.2-exp
Deepseek
81.5
629
128K
¥0 / ¥0Input/Output
63
hunyuan-hy3-preview
Tencent
81.2
334
256K
¥0 / ¥0Input/Output
64
mimo-v2-flash (non-thinking)
Xiaomi
80.9
2.2K
262K
¥0.72 / ¥2.16Input/Output
65
claude-sonnet-4-5-20250929
Anthropic
80.5
3.6K
200K
¥21.6 / ¥108Input/Output
66
claude-opus-4-5-20251101-thinking-32k
Anthropic
80.2
1.8K
200K
¥108 / ¥540Input/Output
67
claude-sonnet-4-5-20250929-thinking-32k
Anthropic
79.9
3.6K
200K
¥21.6 / ¥108Input/Output
68
kimi-k2.5-instant
Moonshot
79.6
242
262K
¥4.32 / ¥21.6Input/Output
69
gpt-5.5-instant
Openai
79.3
1.4K
400K
¥9 / ¥72Input/Output
70
qwen3-vl-235b-a22b-instruct
Alibaba
79.0
494
128K
¥2.16 / ¥8.64Input/Output
71
deepseek-r1-0528
Deepseek
78.7
1K
164K
¥3.6 / ¥15.5Input/Output
72
gpt-5.4-mini-high
Openai
78.4
1.4K
400K
¥5.4 / ¥32.4Input/Output
73
deepseek-v3.1
Deepseek
78.1
1.1K
128K
¥1.44 / ¥5.04Input/Output
74
gemini-3.1-flash-lite-preview
Google
77.8
1.9K
1.05M
¥1.8 / ¥10.8Input/Output
75
deepseek-v3.2
Deepseek
77.5
2.4K
128K
¥2.09 / ¥3.1Input/Output
76
amazon-nova-experimental-chat-26-02-10
Amazon
77.2
213
-
-
77
deepseek-v3.2-exp-thinking
Deepseek
76.9
304
128K
¥0 / ¥0Input/Output
78
gpt-5.2
Openai
76.6
2.2K
400K
¥12.6 / ¥101Input/Output
79
gpt-5.2-high
Openai
76.3
2.4K
400K
¥12.6 / ¥101Input/Output
80
grok-4.1-thinking
Xai
76.0
3.3K
200K
¥14.4 / ¥72Input/Output
81
kimi-k2-thinking-turbo
Moonshot
75.7
3K
262K
¥17.3 / ¥72Input/Output
82
deepseek-v3.2-thinking
Deepseek
75.4
1.9K
128K
¥2.09 / ¥3.1Input/Output
83
gemini-2.5-flash
Google
75.1
6.2K
1.05M
¥2.16 / ¥18Input/Output
84
chatgpt-4o-latest-20250326
Openai
74.8
4.1K
128K
¥18 / ¥72Input/Output
85
gemini-2.5-flash-preview-09-2025
Google
74.5
1.4K
1M
¥2.16 / ¥18Input/Output
86
qwen3-vl-235b-a22b-thinking
Alibaba
74.2
296
131K
¥2.06 / ¥8.26Input/Output
87
mimo-v2-pro
Xiaomi
73.9
1.1K
1.05M
¥7.2 / ¥21.6Input/Output
88
amazon-nova-experimental-chat-12-10
Amazon
73.6
238
-
-
89
mistral-medium-2508
Mistral
73.3
4.7K
262K
¥2.88 / ¥14.4Input/Output
90
grok-3-preview-02-24
Xai
72.9
1.8K
1M
¥9 / ¥18Input/Output
91
grok-4.3
Xai
72.6
787
1M
¥9 / ¥18Input/Output
92
grok-4-1-fast-reasoning
Xai
72.3
2.8K
2M
¥1.44 / ¥3.6Input/Output
93
step-3.5-flash
Stepfun
72.0
1.6K
256K
¥0.69 / ¥2.07Input/Output
94
mistral-large-3
Mistral
71.7
2K
262K
¥3.6 / ¥10.8Input/Output
95
o3-2025-04-16
Openai
71.4
3K
200K
¥14.4 / ¥57.6Input/Output
96
qwen3-30b-a3b-instruct-2507
Alibaba
71.1
1.3K
262K
¥2.16 / ¥3.6Input/Output
97
grok-4-fast-reasoning
Xai
70.8
695
2M
¥1.44 / ¥3.6Input/Output
98
hunyuan-t1-20250711
Tencent
70.5
258
131K
¥0 / ¥0Input/Output
99
glm-4.5-air
Zai
70.2
1.6K
131K
¥0 / ¥0Input/Output
100
nvidia-nemotron-3-super-120b-a12b
Nvidia
69.9
388
262K
¥1.44 / ¥5.76Input/Output
101
mimo-v2-flash (thinking)
Xiaomi
69.6
448
262K
¥0.72 / ¥2.16Input/Output
102
longcat-flash-chat
Meituan
69.3
682
128K
¥1.08 / ¥10.8Input/Output
103
grok-4-0709
Xai
69.0
2K
256K
¥21.6 / ¥108Input/Output
104
minimax-m2.1-preview
Minimax
68.7
821
205K
¥0 / ¥0Input/Output
105
qwen3-max-2025-09-23
Alibaba
68.4
353
258K
¥6.19 / ¥24.7Input/Output
106
qwen3-235b-a22b-no-thinking
Alibaba
68.1
2K
131K
¥2.07 / ¥8.26Input/Output
107
glm-4.7-flash
Zai
67.8
443
200K
¥0 / ¥0Input/Output
108
claude-opus-4-1-20250805
Anthropic
67.5
3.8K
200K
¥108 / ¥540Input/Output
109
gpt-5-high
Openai
67.2
1.6K
400K
¥9 / ¥72Input/Output
110
minimax-m2.7
Minimax
66.9
1.2K
205K
¥0 / ¥0Input/Output
111
gpt-5.3-chat-latest
Openai
66.6
1.6K
128K
¥12.6 / ¥101Input/Output
112
gpt-4.5-preview-2025-02-27
Openai
66.3
907
8.19K
¥216 / ¥432Input/Output
113
gpt-5-chat
Openai
66.0
1.7K
400K
¥9 / ¥72Input/Output
114
claude-opus-4-1-20250805-thinking-16k
Anthropic
65.7
2.6K
200K
¥108 / ¥540Input/Output
115
hunyuan-turbos-20250416
Tencent
65.3
466
131K
¥0 / ¥0Input/Output
116
qwen3-next-80b-a3b-thinking
Alibaba
65.0
718
131K
¥1.04 / ¥10.3Input/Output
117
claude-haiku-4-5-20251001
Anthropic
64.7
3.8K
200K
¥7.2 / ¥36Input/Output
118
kimi-k2-0905-preview
Moonshot
64.4
737
262K
¥4.32 / ¥18Input/Output
119
ling-flash-2.0
Ant Group
64.1
300
131K
¥1.01 / ¥4.1Input/Output
120
amazon-nova-experimental-chat-10-20
Amazon
63.8
606
-
-
121
gpt-5.4-nano-high
Openai
63.5
1.4K
400K
¥1.44 / ¥9Input/Output
122
ring-flash-2.0
Ant Group
63.2
317
131K
¥1.01 / ¥4.1Input/Output
123
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google
62.9
2.2K
1.05M
¥0.72 / ¥2.88Input/Output
124
gemini-2.5-flash-lite-preview-06-17-thinking
Google
62.6
1.7K
65.5K
¥0.72 / ¥2.88Input/Output
125
deepseek-r1
Deepseek
62.3
1.2K
164K
¥5.04 / ¥18Input/Output
126
step-3
Stepfun
62.0
234
65.5K
¥1.8 / ¥4.68Input/Output
127
kimi-k2-0711-preview
Moonshot
61.7
1.6K
131K
¥4.32 / ¥18Input/Output
128
minimax-m2.5
Minimax
61.4
1.9K
205K
¥0 / ¥0Input/Output
129
o1-2024-12-17
Openai
61.1
1.8K
128K
¥108 / ¥432Input/Output
130
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia
60.8
850
131K
¥0 / ¥0Input/Output
131
gpt-5-mini-high
Openai
60.5
1.3K
400K
¥1.8 / ¥14.4Input/Output
132
glm-4-plus-0111
Zai
60.2
387
128K
¥72 / ¥72Input/Output
133
deepseek-v3-0324
Deepseek
59.9
2.5K
75K
¥1.44 / ¥5.76Input/Output
134
claude-opus-4-20250514-thinking-16k
Anthropic
59.6
1.9K
200K
¥108 / ¥540Input/Output
135
claude-opus-4-20250514
Anthropic
59.3
2.4K
200K
¥108 / ¥540Input/Output
136
minimax-m2
Minimax
59.0
278
197K
¥0 / ¥0Input/Output
137
trinity-large-thinking
-
58.7
1.5K
262K
¥1.8 / ¥6.48Input/Output
138
qwen2.5-max
Alibaba
58.4
2K
32K
¥11.5 / ¥46Input/Output
139
qwen3-235b-a22b
Alibaba
58.1
1.3K
131K
¥2.07 / ¥8.26Input/Output
140
grok-3-mini-high
Xai
57.8
718
128K
¥0 / ¥0Input/Output
141
gemini-2.0-flash-001
Google
57.4
2.4K
1.05M
¥1.08 / ¥4.32Input/Output
142
qwq-32b
Alibaba
57.1
1.4K
131K
¥2.07 / ¥6.2Input/Output
143
o3-mini-high
Openai
56.8
1.2K
200K
¥7.92 / ¥31.7Input/Output
144
gpt-oss-120b
Openai
56.5
1.6K
131K
¥1.08 / ¥4.32Input/Output
145
grok-3-mini-beta
Xai
56.2
1.1K
1M
¥9 / ¥18Input/Output
146
mistral-medium-2505
Mistral
55.9
1.6K
262K
¥2.88 / ¥14.4Input/Output
147
gpt-4.1-2025-04-14
Openai
55.6
2.5K
1.05M
¥14.4 / ¥57.6Input/Output
148
nova-2-lite
Amazon
55.3
685
128K
¥2.38 / ¥19.8Input/Output
149
intellect-3
-
55.0
293
131K
¥1.44 / ¥7.92Input/Output
150
step-1o-turbo-202506
Stepfun
54.7
457
-
-
151
minimax-m1
Minimax
54.4
1.8K
1M
¥0.95 / ¥9.03Input/Output
152
qwen3-32b
Alibaba
54.1
187
131K
¥2.07 / ¥8.26Input/Output
153
hunyuan-turbo-0110
Tencent
53.8
208
-
-
154
qwen3-coder-480b-a35b-instruct
Alibaba
53.5
1.4K
262K
¥6.2 / ¥24.8Input/Output
155
qwen3-30b-a3b
Alibaba
53.2
1.3K
128K
¥0.79 / ¥7.78Input/Output
156
claude-sonnet-4-20250514-thinking-32k
Anthropic
52.9
1.8K
200K
¥21.6 / ¥108Input/Output
157
gpt-5-nano-high
Openai
52.6
384
400K
¥0.36 / ¥2.88Input/Output
158
o4-mini-2025-04-16
Openai
52.3
2.3K
200K
¥7.92 / ¥31.7Input/Output
159
trinity-large-preview
-
52.0
1.4K
262K
¥1.8 / ¥6.48Input/Output
160
qwen-plus-0125
Alibaba
51.7
459
1M
¥0.83 / ¥2.07Input/Output
161
gemma-3-27b-it
Google
51.4
2.3K
128K
¥2.15 / ¥2.15Input/Output
162
hunyuan-large-2025-02-10
Tencent
51.1
295
-
-
163
claude-sonnet-4-20250514
Anthropic
50.8
2.2K
200K
¥21.6 / ¥108Input/Output
164
mistral-small-2506
Mistral
50.5
828
262K
¥2.88 / ¥14.4Input/Output
165
gemini-2.0-flash-lite-preview-02-05
Google
50.2
1.5K
1.05M
¥0.54 / ¥2.16Input/Output
166
deepseek-v3
Deepseek
49.8
1.5K
128K
¥0 / ¥0Input/Output
167
gemini-1.5-pro-002
Google
49.5
4.4K
-
-
168
step-2-16k-exp-202412
Stepfun
49.2
328
16.4K
¥37.5 / ¥118Input/Output
169
gpt-4.1-mini-2025-04-14
Openai
48.9
2.1K
1.05M
¥2.88 / ¥11.5Input/Output
170
glm-4.5v
Zai
48.6
173
64K
¥4.32 / ¥13Input/Output
171
o1-preview
Openai
48.3
2.8K
128K
¥108 / ¥432Input/Output
172
command-a-03-2025
Cohere
48.0
3K
256K
¥18 / ¥72Input/Output
173
o3-mini
Openai
47.7
3.4K
200K
¥7.92 / ¥31.7Input/Output
174
hunyuan-turbos-20250226
Tencent
47.4
203
131K
¥0 / ¥0Input/Output
175
hunyuan-standard-2025-02-10
Tencent
47.1
340
-
-
176
yi-lightning
-
46.8
2.7K
12K
¥1.44 / ¥1.44Input/Output
177
deepseek-v2.5-1210
Deepseek
46.5
446
1M
¥1.01 / ¥2.02Input/Output
178
o1-mini
Openai
46.2
4.3K
128K
¥7.92 / ¥31.7Input/Output
179
qwen2.5-plus-1127
Alibaba
45.9
621
-
-
180
gpt-oss-20b
Openai
45.6
488
131K
¥0.32 / ¥1.3Input/Output
181
gemma-3n-e4b-it
Google
45.3
1.2K
128K
¥0 / ¥0Input/Output
182
claude-3-7-sonnet-20250219-thinking-32k
Anthropic
45.0
2K
-
-
183
athene-v2-chat
-
44.7
1.8K
-
-
184
olmo-3.1-32b-instruct
Allenai
44.4
529
200K
¥14.4 / ¥57.6Input/Output
185
claude-3-7-sonnet-20250219
Anthropic
44.1
2.2K
200K
¥21.6 / ¥108Input/Output
186
olmo-3-32b-think
Allenai
43.8
261
128K
¥2.16 / ¥3.24Input/Output
187
glm-4-plus
Zai
43.5
2.4K
128K
¥54 / ¥54Input/Output
188
gemini-1.5-flash-002
Google
43.2
3K
2M
¥0.54 / ¥2.2Input/Output
189
grok-2-2024-08-13
Xai
42.9
5.3K
1M
¥9 / ¥18Input/Output
190
deepseek-v2.5
Deepseek
42.6
2.2K
1M
¥1.01 / ¥2.02Input/Output
191
llama-3.3-nemotron-49b-super-v1
Nvidia
42.2
211
131K
¥0 / ¥0Input/Output
192
gpt-4o-2024-05-13
Openai
41.9
11.4K
128K
¥36 / ¥108Input/Output
193
hunyuan-large-vision
Tencent
41.6
255
-
-
194
gemini-1.5-pro-001
Google
41.3
8.9K
-
-
195
gemini-advanced-0514
Google
41.0
5.9K
-
-
196
llama-4-maverick-17b-128e-instruct
Meta
40.7
2.1K
1M
¥1.8 / ¥6.26Input/Output
197
qwen2.5-72b-instruct
Alibaba
40.4
3.3K
131K
¥4.13 / ¥12.4Input/Output
198
gpt-4.1-nano-2025-04-14
Openai
40.1
246
1.05M
¥14.4 / ¥57.6Input/Output
199
claude-3-5-sonnet-20241022
Anthropic
39.8
6.6K
200K
¥21.6 / ¥108Input/Output
200
claude-3-5-sonnet-20240620
Anthropic
39.5
8.1K
200K
¥21.6 / ¥108Input/Output
201
gpt-4o-mini-2024-07-18
Openai
39.2
5.8K
128K
¥1.08 / ¥4.32Input/Output
202
llama-3.1-nemotron-70b-instruct
Nvidia
38.9
723
128K
¥0 / ¥0Input/Output
203
grok-2-mini-2024-08-13
Xai
38.6
4.5K
1M
¥9 / ¥18Input/Output
204
llama-4-scout-17b-16e-instruct
Meta
38.3
1.6K
128K
¥1.44 / ¥5.62Input/Output
205
gpt-4o-2024-08-06
Openai
38.0
3.8K
128K
¥18 / ¥72Input/Output
206
qwen-max-0919
Alibaba
37.7
1.4K
131K
¥2.48 / ¥9.91Input/Output
207
olmo-3.1-32b-think
Allenai
37.4
491
200K
¥14.4 / ¥57.6Input/Output
208
llama-3.1-tulu-3-70b
Allenai
37.1
224
-
-
209
claude-3-opus-20240229
Anthropic
36.8
23.3K
200K
¥108 / ¥540Input/Output
210
mistral-small-3.1-24b-instruct-2503
Mistral
36.5
1.7K
262K
¥2.88 / ¥14.4Input/Output
211
ibm-granite-h-small
Ibm
36.2
219
-
-
212
amazon-nova-pro-v1.0
Amazon
35.9
1.6K
300K
¥5.76 / ¥23Input/Output
213
gpt-4-1106-preview
Openai
35.6
9.2K
8.19K
¥216 / ¥432Input/Output
214
llama-3.1-405b-instruct-bf16
Meta
35.3
3.1K
128K
¥0 / ¥0Input/Output
215
gpt-4-turbo-2024-04-09
Openai
35.0
10.8K
128K
¥72 / ¥216Input/Output
216
hunyuan-standard-256k
Tencent
34.7
305
-
-
217
reka-core-20240904
-
34.3
598
-
-
218
mistral-large-2407
Mistral
34.0
3.9K
131K
¥14.4 / ¥43.2Input/Output
219
qwen2-72b-instruct
Alibaba
33.7
4.1K
131K
¥4.13 / ¥12.4Input/Output
220
mistral-large-2411
Mistral
33.4
1.9K
128K
¥14.4 / ¥43.2Input/Output
221
athene-70b-0725
-
33.1
1.7K
-
-
222
gpt-4-0125-preview
Openai
32.8
11.4K
8.19K
¥216 / ¥432Input/Output
223
llama-3.1-405b-instruct-fp8
Meta
32.5
5.2K
128K
¥0 / ¥0Input/Output
224
gemini-1.5-flash-001
Google
32.2
7K
2M
¥0.54 / ¥2.2Input/Output
225
gemini-1.5-flash-8b-001
Google
31.9
2.9K
2M
¥0.54 / ¥2.2Input/Output
226
glm-4-0520
Zai
31.6
1.2K
128K
¥108 / ¥108Input/Output
227
command-r-plus-08-2024
Cohere
31.3
845
128K
¥18 / ¥72Input/Output
228
amazon-nova-lite-v1.0
Amazon
31.0
1.3K
300K
¥0.43 / ¥1.73Input/Output
229
magistral-medium-2506
Mistral
30.7
556
128K
¥14.4 / ¥36Input/Output
230
gemma-2-9b-it-simpo
-
30.4
753
8.19K
¥1.44 / ¥1.44Input/Output
231
claude-3-5-haiku-20241022
Anthropic
30.1
4.2K
200K
¥5.76 / ¥28.8Input/Output
232
qwen2.5-coder-32b-instruct
Alibaba
29.8
528
131K
¥2.07 / ¥6.2Input/Output
233
gemma-2-27b-it
Google
29.5
6.9K
8.19K
¥0.58 / ¥0.58Input/Output
234
reka-flash-20240904
-
29.2
607
65.5K
¥0.72 / ¥1.44Input/Output
235
qwq-32b-preview
Alibaba
28.9
206
131K
¥2.07 / ¥6.2Input/Output
236
llama-3.3-70b-instruct
Meta
28.6
3.4K
128K
¥0 / ¥0Input/Output
237
llama-3.1-70b-instruct
Meta
28.3
4.8K
131K
¥2.88 / ¥2.88Input/Output
238
nemotron-4-340b-instruct
Nvidia
28.0
2.4K
-
-
239
yi-1.5-34b-chat
-
27.7
2.9K
-
-
240
phi-4
Microsoft
27.4
1.5K
128K
¥0.9 / ¥3.6Input/Output
241
c4ai-aya-expanse-32b
Cohere
27.1
2.4K
-
-
242
amazon-nova-micro-v1.0
Amazon
26.7
1.3K
128K
¥0.25 / ¥1.01Input/Output
243
qwen1.5-110b-chat
Alibaba
26.4
2.9K
-
-
244
mistral-small-24b-instruct-2501
Mistral
26.1
1.1K
262K
¥2.88 / ¥14.4Input/Output
245
jamba-1.5-large
-
25.8
675
256K
¥0 / ¥0Input/Output
246
deepseek-coder-v2
Deepseek
25.5
1.7K
1M
¥1.01 / ¥2.02Input/Output
247
internlm2_5-20b-chat
-
25.2
959
-
-
248
ministral-8b-2410
Mistral
24.9
478
128K
¥0.72 / ¥0.72Input/Output
249
olmo-2-0325-32b-instruct
Allenai
24.6
229
-
-
250
command-r-plus
Cohere
24.3
10.5K
128K
¥18 / ¥72Input/Output
251
claude-3-sonnet-20240229
Anthropic
24.0
15.6K
200K
¥21.6 / ¥108Input/Output
252
qwen1.5-72b-chat
Alibaba
23.7
4.2K
-
-
253
gemma-2-9b-it
Google
23.4
5K
8.19K
¥1.44 / ¥1.44Input/Output
254
gpt-4-0314
Openai
23.1
5.8K
8.19K
¥216 / ¥432Input/Output
255
command-r-08-2024
Cohere
22.8
834
128K
¥18 / ¥72Input/Output
256
c4ai-aya-expanse-8b
Cohere
22.5
618
-
-
257
llama-3.1-nemotron-51b-instruct
Nvidia
22.2
403
128K
¥0 / ¥0Input/Output
258
qwen1.5-32b-chat
Alibaba
21.9
3.2K
-
-
259
llama-3.1-tulu-3-8b
Allenai
21.6
238
-
-
260
yi-34b-chat
-
21.3
1.2K
-
-
261
claude-3-haiku-20240307
Anthropic
21.0
16.7K
200K
¥1.8 / ¥9Input/Output
262
llama-3.1-8b-instruct
Meta
20.7
4.4K
131K
¥0.79 / ¥0.79Input/Output
263
qwen1.5-14b-chat
Alibaba
20.4
3.2K
-
-
264
command-r
Cohere
20.1
8.2K
128K
¥18 / ¥72Input/Output
265
granite-3.1-8b-instruct
Ibm
19.8
211
-
-
266
reka-flash-21b-20240226-online
-
19.5
2K
-
-
267
qwen1.5-7b-chat
Alibaba
19.1
417
-
-
268
granite-3.1-2b-instruct
Ibm
18.8
231
-
-
269
gpt-4-0613
Openai
18.5
8.5K
8.19K
¥216 / ¥432Input/Output
270
jamba-1.5-mini
-
18.2
711
256K
¥0 / ¥0Input/Output
271
reka-flash-21b-20240226
-
17.9
2.8K
-
-
272
gemma-2-2b-it
Google
17.6
3.8K
128K
¥0 / ¥0Input/Output
273
deepseek-llm-67b-chat
Deepseek
17.3
211
1M
¥1.01 / ¥2.02Input/Output
274
gemini-pro-dev-api
Google
17.0
1.9K
1.05M
¥14.4 / ¥86.4Input/Output
275
mistral-large-2402
Mistral
16.7
7.8K
262K
¥2.88 / ¥14.4Input/Output
276
mixtral-8x22b-instruct-v0.1
Mistral
16.4
5.7K
64K
¥14.4 / ¥43.2Input/Output
277
llama-3-70b-instruct
Meta
16.1
15.9K
8.19K
¥3.67 / ¥5.33Input/Output
278
starling-lm-7b-beta
-
15.8
2.9K
200K
¥5.4 / ¥18.7Input/Output
279
mistral-medium
Mistral
15.5
3K
262K
¥2.88 / ¥14.4Input/Output
280
phi-3-medium-4k-instruct
Microsoft
15.2
2.8K
4.1K
¥1.22 / ¥4.9Input/Output
281
gemini-pro
Google
14.9
236
1.05M
¥14.4 / ¥86.4Input/Output
282
openchat-3.5-0106
-
14.6
1.5K
-
-
283
zephyr-orpo-141b-A35b-v0.1
-
14.3
657
200K
¥108 / ¥432Input/Output
284
chatglm-6b
-
14.0
267
200K
¥5.4 / ¥18.7Input/Output
285
qwen-14b-chat
Alibaba
13.7
195
32.8K
¥1.04 / ¥3.1Input/Output
286
llama-3-8b-instruct
Meta
13.4
10.8K
8.19K
¥0.29 / ¥0.29Input/Output
287
gpt-3.5-turbo-0125
Openai
13.1
7.6K
16.4K
¥3.6 / ¥10.8Input/Output
288
openchat-3.5
-
12.8
322
-
-
289
granite-3.0-2b-instruct
Ibm
12.5
759
-
-
290
dbrx-instruct-preview
-
12.2
5K
-
-
291
snowflake-arctic-instruct
-
11.9
3.1K
-
-
292
chatglm3-6b
-
11.6
189
200K
¥5.4 / ¥18.7Input/Output
293
granite-3.0-8b-instruct
Ibm
11.2
701
-
-
294
phi-3-small-8k-instruct
Microsoft
10.9
2.4K
8.19K
¥1.08 / ¥4.32Input/Output
295
gemma-1.1-7b-it
Google
10.6
3.2K
-
-
296
mixtral-8x7b-instruct-v0.1
Mistral
10.3
8.3K
32K
¥5.04 / ¥5.04Input/Output
297
wizardlm-70b
Microsoft
10.0
334
-
-
298
starling-lm-7b-alpha
-
9.7
858
200K
¥5.4 / ¥18.7Input/Output
299
vicuna-13b
-
9.4
1.2K
-
-
300
vicuna-33b
-
9.1
1.4K
-
-
301
gemma-7b-it
Google
8.8
1K
-
-
302
phi-3-mini-4k-instruct-june-2024
Microsoft
8.5
1.2K
4.1K
¥0.94 / ¥3.74Input/Output
303
qwen1.5-4b-chat
Alibaba
8.2
1K
-
-
304
wizardlm-13b
Microsoft
7.9
287
-
-
305
phi-3-mini-4k-instruct
Microsoft
7.6
2.3K
4.1K
¥0.94 / ¥3.74Input/Output
306
llama-3.2-3b-instruct
Meta
7.3
721
131K
¥0.22 / ¥0.35Input/Output
307
phi-3-mini-128k-instruct
Microsoft
7.0
2K
128K
¥0.94 / ¥3.74Input/Output
308
openhermes-2.5-mistral-7b
-
6.7
205
1M
¥36 / ¥180Input/Output
309
olmo-7b-instruct
Allenai
6.4
722
-
-
310
tulu-2-dpo-70b
-
6.1
274
-
-
311
gpt-3.5-turbo-1106
Openai
5.8
708
16.4K
¥7.2 / ¥14.4Input/Output
312
gemma-1.1-2b-it
Google
5.5
1.3K
-
-
313
mistral-7b-instruct-v0.2
Mistral
5.2
2K
262K
¥2.88 / ¥14.4Input/Output
314
llama-2-13b-chat
Meta
4.9
1.2K
-
-
315
llama-2-70b-chat
Meta
4.6
3.6K
-
-
316
gemma-2b-it
Google
4.3
598
-
-
317
vicuna-7b
-
4.0
335
-
-
318
codellama-34b-instruct
Meta
3.6
249
-
-
319
llama-2-7b-chat
Meta
3.3
956
128K
¥4.03 / ¥48Input/Output
320
zephyr-7b-beta
-
3.0
373
-
-
321
llama-3.2-1b-instruct
Meta
2.7
674
16.4K
¥0.07 / ¥0.08Input/Output
322
mpt-7b-chat
-
2.4
178
-
-
323
mistral-7b-instruct
Mistral
2.1
274
262K
¥2.88 / ¥14.4Input/Output
324
RWKV-4-Raven-14B
-
1.8
218
-
-
325
palm-2
Google
1.5
355
-
-
326
koala-13b
-
1.2
374
-
-
327
dolly-v2-12b
-
0.9
177
-
-
328
oasst-pythia-12b
-
0.6
321
-
-
329
alpaca-13b
-
0.3
263
-
-
330
fastchat-t5-3b
-
0.0
224
-
-
Top model analysis

gpt-5.5 why it ranks first

gpt-5.5 ranks first with a percent score of 100.0 and 808 samples. Use it as the first option for this leaderboard, then compare price, context and availability.

How to choose

Do not only look at rank #1

Start with the leaderboard closest to your task. Compare the top models by score and sample size, then check price, context length, open or closed access, and provider availability.

FAQ

FAQ

中文排行榜看什么指标?

主要看排名、百分制分数、样本量和来源。分数用于快速比较同一榜单内模型表现,样本量用于判断结果稳定性。

为什么不同榜单不能直接混合成总分?

不同榜单的任务、样本和评测口径不同,模力榜默认只在同一榜单内排序,避免把写作、代码、图像等能力强行合并。

中文模型应该怎么选?

优先看与你任务最接近的榜单,再结合价格、上下文长度、开源闭源和厂商可用性。排名靠前不代表适合所有预算和部署方式。

榜单多久更新?

页面展示的是最新成功采集的公开榜单数据。当前优先使用 LMArena leaderboard dataset,并在页面来源中保留原始链接。